14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

MODIS: An Audio Motif Discovery Software

Laurence Catanese (1), Nathan Souviraà-Labastie (2), Bingqing Qu (2), Sebastien Campion (1), Guillaume Gravier (2), Emmanuel Vincent (1), Frédéric Bimbot (2)

(1) INRIA, France
(2) IRISA, France

MODIS is a free speech and audio motif discovery software developed at IRISA Rennes. Motif discovery is the task of discovering and collecting occurrences of repeating patterns in the absence of prior knowledge, or training material. MODIS is based on a generic approach to mine repeating audio sequences, with tolerance to motif variability. The algorithm implementation allows to process large audio streams at a reasonable speed where motif discovery often requires huge amount of time.

Full Paper

Bibliographic reference.  Catanese, Laurence / Souviraà-Labastie, Nathan / Qu, Bingqing / Campion, Sebastien / Gravier, Guillaume / Vincent, Emmanuel / Bimbot, Frédéric (2013): "MODIS: an audio motif discovery software", In INTERSPEECH-2013, 2675-2677.